A review of deep learning and machine learning techniques for hydrological inflow forecasting

• Main Authors: Latif S.D., Ahmed A.N.
• Other Authors: 57216081524
• Format: Review
• Published: Springer Science and Business Media B.V. 2024
• Subjects: Deep learning; Long short-term memory (LSTM); Machine learning; Streamflow prediction; algorithm; forecasting method; inflow; literature review; machine learning; prediction; rainfall; reservoir; streamflow

Conventional machine learning models have been widely used for reservoir inflow and rainfall prediction. Nowadays, researchers focus on a new computing architecture in the area of AI, namely, deep learning for hydrological forecasting parameters. This review paper tends to broadcast more of the intriguing interest in reservoir inflow prediction utilizing deep learning and machine learning algorithms. The AI models utilized for different hydrology sectors, as well as the most prevalent machine learning techniques, will be explored in this thorough study, which divides AI techniques into two primary categories: deep learning and machine learning. In this study, we look at the long short-term memory deep learning method as well as three traditional machine learning algorithms: support vector machine, random forest, and boosted regression tree. Under each part, a summary of the findings is provided. For convenience of reference, some of the benefits and drawbacks discovered through literature reviews have been listed. Finally, future recommendations and overall conclusions based on research findings are given. This review focuses on papers from high-impact factor periodicals published over a 4�years period beginning in 2018 onwards. � 2023, The Author(s), under exclusive licence to Springer Nature B.V.